ResearchTrend.AI
Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness

Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness

Ailin Deng
Shen Li
Miao Xiong
Zhirui Chen
Bryan Hooi
ArXivPDFHTML

Papers citing "Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness"

5 / 5 papers shown
Title
What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?
What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?
Weijie Tu
Weijian Deng
Liang Zheng
Tom Gedeon
44
0
0
14 Jun 2024
Generalized Out-of-Distribution Detection: A Survey
Generalized Out-of-Distribution Detection: A Survey
Jingkang Yang
Kaiyang Zhou
Yixuan Li
Ziwei Liu
193
881
0
21 Oct 2021
Unsolved Problems in ML Safety
Unsolved Problems in ML Safety
Dan Hendrycks
Nicholas Carlini
John Schulman
Jacob Steinhardt
186
276
0
28 Sep 2021
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Balaji Lakshminarayanan
Alexander Pritzel
Charles Blundell
UQCV
BDL
276
5,683
0
05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Y. Gal
Zoubin Ghahramani
UQCV
BDL
287
9,156
0
06 Jun 2015